CN113139028A - Method for predicting delivery address - Google Patents
Method for predicting delivery address Download PDFInfo
- Publication number
- CN113139028A CN113139028A CN202110439512.8A CN202110439512A CN113139028A CN 113139028 A CN113139028 A CN 113139028A CN 202110439512 A CN202110439512 A CN 202110439512A CN 113139028 A CN113139028 A CN 113139028A
- Authority
- CN
- China
- Prior art keywords
- address
- street
- delivery
- preprocessed
- receiving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 230000002860 competitive effect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of distribution address prediction, in particular to a distribution address prediction method, which comprises the steps of obtaining a delivery address of a target express; preprocessing the receiving address by using the jieba word to obtain a preprocessed receiving address; inputting the preprocessed delivery address into a pre-trained classification network model to obtain a predicted first street address; performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance; if the first street address and the second street address are the same address, the address is used as a distribution address, the problems that the street name does not exist in the address and the street name is wrong are solved, the dispatch efficiency of the courier is improved, and packages on the same street can be dispatched in a unified mode.
Description
Technical Field
The invention relates to the technical field of delivery address prediction, in particular to a delivery address prediction method.
Background
In recent years, express delivery industry is developed at a high speed, daily delivery volume reaches more than 4000 ten thousand, the delivery efficiency of a terminal courier is directly determined by address filling standard degree, and good user experience can be brought only by maximizing the delivery efficiency of the courier.
In the prior art, regular matching is performed according to an existing administrative division address. However, in actual operation, a large number of problems of irregular writing of harvest addresses, wrong writing, disordered addresses, a plurality of administrative areas of the same level and the like exist, and the distribution efficiency of the terminal couriers is greatly reduced.
Disclosure of Invention
In view of the above, the present invention provides a method for predicting delivery addresses, so as to overcome the problems of irregular writing, wrong writing, disordered addresses, multiple administrative areas of the same level, and the like of a large number of harvest addresses in current actual operations, and greatly reduce the delivery efficiency of a terminal courier.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method of predicting a delivery address, comprising:
acquiring a receiving address of a target express;
preprocessing the receiving address by using a jieba word to obtain a preprocessed receiving address;
inputting the preprocessed delivery address into a pre-trained classification network model to obtain a predicted first street address; performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance;
and if the first street address and the second street address are the same address, taking the address as a distribution address.
Further, the above method for predicting a delivery address, where the receiving address is preprocessed by using a jieba part word to obtain a preprocessed receiving address, includes:
and dividing the receiving address by using jieba word division, filtering repeated address fields, and converting traditional characters in the receiving address into simplified characters to obtain the preprocessed receiving address.
Further, according to the method for predicting a delivery address, if the first street address and the second street address are not the same address, an abnormal alert is output;
acquiring information fed back by a user according to the abnormal reminding;
and determining the first street address or the second street address as the delivery address according to information fed back by a user.
Further, the method for predicting a delivery address as described above further includes:
and sending the delivery address to a corresponding terminal courier so that the terminal courier delivers the express according to the delivery address.
Further, the method for predicting a delivery address as described above further includes:
and inputting a preset training sample into the neural network model for training to obtain the trained classification network model.
Further, in the method for predicting a delivery address described above, the neural network model includes textcnn.
The method for predicting the delivery address comprises the steps of obtaining a receiving address of a target express; preprocessing the receiving address by using the jieba word to obtain a preprocessed receiving address; inputting the preprocessed delivery address into a pre-trained classification network model to obtain a predicted first street address; performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance; if the first street address and the second street address are the same address, the address is used as a distribution address, the problems that the street name does not exist in the address and the street name is wrong are solved, other position information in the address is fully utilized to predict the street, the distribution efficiency of couriers is improved, and packages on the same street can be uniformly distributed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting a dispatch address according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
FIG. 1 is a flow chart of a method for predicting a dispatch address according to an embodiment of the present invention. Referring to fig. 1, the present embodiment may include the following steps:
and S11, acquiring the delivery address of the target express.
In some alternative embodiments, the shipping address of the target courier to be delivered may be obtained first. For example, the shipping address of the target courier that needs to be delivered the next day may be pulled.
And S12, preprocessing the receiving address by using the jieba word to obtain the preprocessed receiving address.
And preprocessing the receiving address by using the jieba word. In some optional embodiments, the pre-processing comprises the following steps:
and segmenting the receiving address by using jieba word segmentation, filtering repeated address fields, and converting traditional characters in the receiving address into simplified characters to obtain the preprocessed receiving address.
Specifically, the jieba participle is a Python Chinese participle component, can perform functions such as participle, part of speech tagging, keyword extraction and the like on a Chinese text, and supports a user-defined dictionary. For example, the rich building 3201 room in the competitive show area of the baoding city of Hebei province may be divided into "Hebei province", "baoding city", "competitive show area", "rich building 3201 room". Wherein the 'competitive show area' and the 'competitive show area' are repeated address fields, one group of the 'competitive show areas' is filtered, and the processed goods receiving addresses 'Hebei province', 'baoding city', 'competitive show area', 'affluent mansion 3201 room' are obtained. If the original complex form character exists in the receiving address, the original complex form character can be automatically converted into a simplified form character.
And S13, inputting the pre-processed delivery address into a pre-trained classification network model to obtain the predicted first street address.
And inputting the processed delivery address into a pre-trained classification network model to obtain a result output from the classification model, and taking the result as a first street address.
Wherein the classification network model is trained by a neural network model, and in some alternative embodiments, the neural network model comprises textcnn. Preset training samples are input into textcnn for training. The training samples are area names and corresponding street names. And training the textcnn by using the training set, testing by using the testing set, and finishing training when the test result is converged to obtain the classification network model.
For example, "Hebei province", "baoding city", "competitive district", "Rich building 3201 room" may be input to the classification network model, and the output result "Pioneer street" may be obtained as the first street address.
Other models than textcnn may be used, but the conditions of aging and accuracy need to be considered.
And S14, performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance.
And determining the longitude and latitude corresponding to the receiving address according to the preprocessed receiving address, performing Euclidean distance calculation on the longitude and latitude and the longitude and latitude of the national administrative street, and taking the street with the shortest Euclidean distance as a second street address.
It should be noted that, the present embodiment does not limit the execution sequence of S13 and S14, and S13 may be executed first, and then S14 may be executed; s14 may be executed first, and then S13 may be executed, which is not limited in this embodiment.
And S15, if the first street address and the second street address are the same address, the address is used as a distribution address.
And further judging whether the first street address and the second street address are the same address, and if the first street address and the second street address are the same address, using the address as a distribution address.
The method for predicting the delivery address comprises the steps of obtaining a receiving address of a target express; preprocessing the receiving address by using the jieba word to obtain a preprocessed receiving address; inputting the preprocessed delivery address into a pre-trained classification network model to obtain a predicted first street address; performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance; if the first street address and the second street address are the same address, the address is used as a distribution address, the problems that the street name does not exist in the address and the street name is wrong are solved, other position information in the address is fully utilized to predict the street, the distribution efficiency of couriers is improved, and packages on the same street can be uniformly distributed.
In some optional embodiments, the following steps may be further included:
step one, if the first street address and the second street address are not the same address, outputting an abnormal prompt;
step two, obtaining information fed back by the user according to the abnormal reminding;
and step three, determining the first street address or the second street address as a distribution address according to the information fed back by the user.
Specifically, if the first street address and the second street address are not the same address, an exception reminder may be output, and the user manually selects the first street address or the second street address as the delivery address according to the exception reminder. In this embodiment, information fed back by the user is obtained, and the first street address or the second street address is determined as a distribution address according to the information fed back by the user.
For example, if the user feedback is to select the first street address as the delivery address, then the first street address is determined to be the delivery address. And if the user feedbacks to select the second street address as the delivery address, determining the second street address as the delivery address.
In some alternative embodiments, the first street address may be directly used as the shipping address when the first street address and the second street address are not the same address.
In some optional embodiments, after determining the shipping address, the following steps may be further included:
and sending the delivery address to a corresponding terminal courier so that the terminal courier delivers the express according to the delivery address.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (6)
1. A method for predicting a delivery address, comprising:
acquiring a receiving address of a target express;
preprocessing the receiving address by using a jieba word to obtain a preprocessed receiving address;
inputting the preprocessed delivery address into a pre-trained classification network model to obtain a predicted first street address; performing Euclidean distance calculation by using the longitude and latitude corresponding to the preprocessed delivery address and the longitude and latitude of the national administrative street, and determining a second street address with the shortest Euclidean distance;
and if the first street address and the second street address are the same address, taking the address as a distribution address.
2. The method for predicting a delivery address of claim 1, wherein the preprocessing the shipping address using jieba part words to obtain a preprocessed shipping address comprises:
and dividing the receiving address by using jieba word division, filtering repeated address fields, and converting traditional characters in the receiving address into simplified characters to obtain the preprocessed receiving address.
3. The method of claim 1, wherein if the first street address and the second street address are not the same address, outputting an exception alert;
acquiring information fed back by a user according to the abnormal reminding;
and determining the first street address or the second street address as the delivery address according to information fed back by a user.
4. The method of predicting a delivery address of claim 1, further comprising:
and sending the delivery address to a corresponding terminal courier so that the terminal courier delivers the express according to the delivery address.
5. The method of predicting a delivery address of claim 1, further comprising:
and inputting a preset training sample into the neural network model for training to obtain the trained classification network model.
6. The method of claim 5 wherein the neural network model comprises textcnn.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110439512.8A CN113139028A (en) | 2021-04-23 | 2021-04-23 | Method for predicting delivery address |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110439512.8A CN113139028A (en) | 2021-04-23 | 2021-04-23 | Method for predicting delivery address |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113139028A true CN113139028A (en) | 2021-07-20 |
Family
ID=76811869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110439512.8A Pending CN113139028A (en) | 2021-04-23 | 2021-04-23 | Method for predicting delivery address |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139028A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255564A (en) * | 2017-07-13 | 2019-01-22 | 菜鸟智能物流控股有限公司 | Pick-up point address recommendation method and device |
| CN110069626A (en) * | 2017-11-09 | 2019-07-30 | 菜鸟智能物流控股有限公司 | Target address recognition method, classification model training method and device |
| CN111241229A (en) * | 2020-01-20 | 2020-06-05 | 上海东普信息科技有限公司 | Express courier station address distinguishing method, computer equipment and storage medium |
| CN112199501A (en) * | 2020-10-13 | 2021-01-08 | 华中科技大学 | Scientific and technological information text classification method |
-
2021
- 2021-04-23 CN CN202110439512.8A patent/CN113139028A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255564A (en) * | 2017-07-13 | 2019-01-22 | 菜鸟智能物流控股有限公司 | Pick-up point address recommendation method and device |
| CN110069626A (en) * | 2017-11-09 | 2019-07-30 | 菜鸟智能物流控股有限公司 | Target address recognition method, classification model training method and device |
| CN111241229A (en) * | 2020-01-20 | 2020-06-05 | 上海东普信息科技有限公司 | Express courier station address distinguishing method, computer equipment and storage medium |
| CN112199501A (en) * | 2020-10-13 | 2021-01-08 | 华中科技大学 | Scientific and technological information text classification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909654B (en) | Multi-level classification system and method based on news text information | |
| CN111414479B (en) | Label extraction method based on short text clustering technology | |
| CN107766371B (en) | Text information classification method and device | |
| US9342588B2 (en) | Reclassification of training data to improve classifier accuracy | |
| CN106598999B (en) | Method and device for calculating text theme attribution degree | |
| CN107291840B (en) | User attribute prediction model construction method and device | |
| CN109597874B (en) | Information recommendation method, device and server | |
| CN111651996A (en) | Abstract generation method and device, electronic equipment and storage medium | |
| CN111815432B (en) | Financial service risk prediction method and device | |
| CN110659367B (en) | Text classification number determination method and device and electronic equipment | |
| CN111523433B (en) | Standardized processing method, device and equipment for end address of express mail | |
| CN111680506A (en) | External key mapping method and device of database table, electronic equipment and storage medium | |
| CN110532449B (en) | Method, device, equipment and storage medium for processing service document | |
| CN111143517A (en) | Method, device, equipment and storage medium for predicting human-selected label | |
| CN112395858B (en) | Multi-knowledge point labeling method and system integrating test question data and answer data | |
| CN113139028A (en) | Method for predicting delivery address | |
| CN111325495B (en) | Abnormal part classification method and system | |
| CN115618043B (en) | Text operation graph mutual inspection method and model training method, device, equipment and medium | |
| CN111916063A (en) | Sequencing method, training method, system and storage medium based on BPE (Business Process Engineer) coding | |
| CN116306974A (en) | Model training method and device of question-answering system, electronic equipment and storage medium | |
| CN110825874A (en) | Chinese text classification method and device and computer readable storage medium | |
| CN115730591A (en) | User service method, device, equipment and storage medium based on knowledge graph | |
| CN111930959A (en) | Method and device for generating text by using map knowledge | |
| CN110968690B (en) | Clustering division method and device for words, equipment and storage medium | |
| CN111930911B (en) | Rapid field question-answering method and device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |